LangChain Quickstart¶

In this quickstart you will create a simple LCEL Chain and learn how to log it and get feedback on an LLM response.

For evaluation, we will leverage the RAG triad of groundedness, context relevance and answer relevance.

Setup¶

Add API keys¶

For this quickstart you will need an Open AI key

In [ ]:

# !pip install trulens trulens-apps-langchain trulens-providers-openai openai langchain langchainhub langchain-openai langchain_community faiss-cpu bs4 tiktoken

# !pip install trulens trulens-apps-langchain trulens-providers-openai openai langchain langchainhub langchain-openai langchain_community faiss-cpu bs4 tiktoken

In [ ]:

import os

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = "sk-proj-..."

os.environ["TRULENS_OTEL_TRACING"] = "1"

import os if "OPENAI_API_KEY" not in os.environ: os.environ["OPENAI_API_KEY"] = "sk-proj-..." os.environ["TRULENS_OTEL_TRACING"] = "1"

Import from LangChain and TruLens¶

In [ ]:

# Imports main tools:
from trulens.apps.langchain import TruChain
from trulens.core import TruSession

session = TruSession()
session.reset_database()

# Imports main tools: from trulens.apps.langchain import TruChain from trulens.core import TruSession session = TruSession() session.reset_database()

In [ ]:

# Imports from LangChain to build app
import bs4
from langchain import hub
from langchain.chat_models import ChatOpenAI
from langchain.document_loaders import WebBaseLoader
from langchain.schema import StrOutputParser
from langchain_core.runnables import RunnablePassthrough

# Imports from LangChain to build app import bs4 from langchain import hub from langchain.chat_models import ChatOpenAI from langchain.document_loaders import WebBaseLoader from langchain.schema import StrOutputParser from langchain_core.runnables import RunnablePassthrough

Load documents¶

In [ ]:

loader = WebBaseLoader(
    web_paths=("https://lilianweng.github.io/posts/2023-06-23-agent/",),
    bs_kwargs=dict(
        parse_only=bs4.SoupStrainer(
            class_=("post-content", "post-title", "post-header")
        )
    ),
)
docs = loader.load()

loader = WebBaseLoader( web_paths=("https://lilianweng.github.io/posts/2023-06-23-agent/",), bs_kwargs=dict( parse_only=bs4.SoupStrainer( class_=("post-content", "post-title", "post-header") ) ), ) docs = loader.load()

Create Vector Store¶

In [ ]:

from langchain_community.vectorstores import FAISS
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter

embeddings = OpenAIEmbeddings()


text_splitter = RecursiveCharacterTextSplitter()
documents = text_splitter.split_documents(docs)
vectorstore = FAISS.from_documents(documents, embeddings)

from langchain_community.vectorstores import FAISS from langchain_openai import OpenAIEmbeddings from langchain_text_splitters import RecursiveCharacterTextSplitter embeddings = OpenAIEmbeddings() text_splitter = RecursiveCharacterTextSplitter() documents = text_splitter.split_documents(docs) vectorstore = FAISS.from_documents(documents, embeddings)

Create RAG¶

In [ ]:

retriever = vectorstore.as_retriever()

prompt = hub.pull("rlm/rag-prompt")
llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0)


def format_docs(docs):
    return "\n\n".join(doc.page_content for doc in docs)


rag_chain = (
    {"context": retriever | format_docs, "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)

retriever = vectorstore.as_retriever() prompt = hub.pull("rlm/rag-prompt") llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0) def format_docs(docs): return "\n\n".join(doc.page_content for doc in docs) rag_chain = ( {"context": retriever | format_docs, "question": RunnablePassthrough()} | prompt | llm | StrOutputParser() )

Send your first request¶

In [ ]:

rag_chain.invoke("What is Task Decomposition?")

rag_chain.invoke("What is Task Decomposition?")

Initialize Feedback Function(s)¶

In [ ]:

import numpy as np
from trulens.core import Feedback
from trulens.providers.openai import OpenAI

provider = OpenAI(model_engine="gpt-4.1-mini")

# Define a groundedness feedback function
f_groundedness = (
    Feedback(
        provider.groundedness_measure_with_cot_reasons, name="Groundedness"
    )
    .on_context(collect_list=True)
    .on_output()
)
# Question/answer relevance between overall question and answer.
f_answer_relevance = (
    Feedback(provider.relevance_with_cot_reasons, name="Answer Relevance")
    .on_input()
    .on_output()
)

# Context relevance between question and each context chunk.
f_context_relevance = (
    Feedback(
        provider.context_relevance_with_cot_reasons, name="Context Relevance"
    )
    .on_input()
    .on_context(collect_list=False)
    .aggregate(np.mean)  # choose a different aggregation method if you wish
)

import numpy as np from trulens.core import Feedback from trulens.providers.openai import OpenAI provider = OpenAI(model_engine="gpt-4.1-mini") # Define a groundedness feedback function f_groundedness = ( Feedback( provider.groundedness_measure_with_cot_reasons, name="Groundedness" ) .on_context(collect_list=True) .on_output() ) # Question/answer relevance between overall question and answer. f_answer_relevance = ( Feedback(provider.relevance_with_cot_reasons, name="Answer Relevance") .on_input() .on_output() ) # Context relevance between question and each context chunk. f_context_relevance = ( Feedback( provider.context_relevance_with_cot_reasons, name="Context Relevance" ) .on_input() .on_context(collect_list=False) .aggregate(np.mean) # choose a different aggregation method if you wish )

Instrument chain for logging with TruLens¶

In [ ]:

tru_recorder = TruChain(
    rag_chain,
    app_name="ChatApplication",
    app_version="Base",
    feedbacks=[f_answer_relevance, f_context_relevance, f_groundedness],
)

tru_recorder = TruChain( rag_chain, app_name="ChatApplication", app_version="Base", feedbacks=[f_answer_relevance, f_context_relevance, f_groundedness], )

In [ ]:

with tru_recorder as recording:
    llm_response = rag_chain.invoke("What is Task Decomposition?")

display(llm_response)

with tru_recorder as recording: llm_response = rag_chain.invoke("What is Task Decomposition?") display(llm_response)

Check results

In [ ]:

session.get_leaderboard()

session.get_leaderboard()

In [ ]:

from trulens.dashboard import run_dashboard

run_dashboard(session=session)

from trulens.dashboard import run_dashboard run_dashboard(session=session)